Demand forecasting in supply chain: The impact of demand volatility in the presence of promotion

Mahdi Abolghasemi, Eric J. Beh, Garth Tarr, Richard Gerlach

Abstract: Highlights•The association between time series features and demand volatility is objectively examined.•Demand volatility is shown to significantly impacts the accuracy of forecasts.•A hybrid model is proposed to forecast highly volatile demands.•The robustness of statistical and machine learning models is empirically evaluated.•An empirical analysis is provided with insights for researchers and practitioners.